© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15039
    Prev
    Next
    INDEX
    Explanations

    way to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¿ŀäºij
    -0.09
    .firstChild
    -0.08
    nam
    -0.08
    uiu
    -0.08
    hoven
    -0.08
    uting
    -0.08
    ìĿ´ìĸ´
    -0.08
    BaseContext
    -0.08
    ziÄĻ
    -0.08
    dale
    -0.08
    POSITIVE LOGITS
     {@
    0.07
     ers
    0.07
    æłĩ
    0.06
    çĪ±ä¸į
    0.06
    æłĩ示
    0.06
    ...
    0.06
    åħ¼åħ·
    0.06
    im
    0.06
    åĩºåħ·
    0.06
    缸å¾ħ
    0.06
    Activations Density 0.003%

    No Known Activations